The Coronavirus Disease 2019 (COVID-19) has a profound impact on global health and economy, making it crucial to build accurate and interpretable data-driven predictive models for COVID-19 cases to improve policy making. The extremely large scale of the pandemic and the intrinsically changing transmission characteristics pose great challenges for effective COVID-19 case prediction. To address this challenge, we propose a novel hybrid model in which the interpretability of the Autoregressive model (AR) and the predictive power of the long short-term memory neural networks (LSTM) join forces. The proposed hybrid model is formalized as a neural network with an architecture that connects two composing model blocks, of which the relative contribution is decided data-adaptively in the training procedure. We demonstrate the favorable performance of the hybrid model over its two component models as well as other popular predictive models through comprehensive numerical studies on two data sources under multiple evaluation metrics. Specifically, in county-level data of 8 California counties, our hybrid model achieves 4.173% MAPE on average, outperforming the composing AR (5.629%) and LSTM (4.934%). In country-level datasets, our hybrid model outperforms the widely-used predictive models - AR, LSTM, SVM, Gradient Boosting, and Random Forest - in predicting COVID-19 cases in 8 countries around the world. In addition, we illustrate the interpretability of our proposed hybrid model, a key feature not shared by most black-box predictive models for COVID-19 cases. Our study provides a new and promising direction for building effective and interpretable data-driven models, which could have significant implications for public health policy making and control of the current and potential future pandemics.

翻译：新型冠状病毒肺炎（COVID-19）对全球健康和经济产生了深远影响，因此构建准确且可解释的数据驱动预测模型对于改进政策制定至关重要。疫情的庞大规模以及传播特征的内在动态变化对有效的COVID-19病例预测提出了巨大挑战。为应对这一挑战，我们提出了一种新型混合模型，该模型融合了自回归模型（AR）的可解释性和长短期记忆神经网络（LSTM）的预测能力。所提出的混合模型被形式化为一种神经网络架构，连接了两个组成模型模块，其相对贡献在训练过程中根据数据自适应地确定。通过在多个评估指标下对两个数据源的全面数值研究，我们证明了该混合模型相较于其两个组成模型及其他流行预测模型的优异性能。具体而言，在加利福尼亚州8个县的县级数据中，我们的混合模型平均实现了4.173%的平均绝对百分比误差（MAPE），优于其组成模型AR（5.629%）和LSTM（4.934%）。在国家层面数据集中，我们的混合模型在预测全球8个国家的COVID-19病例方面优于广泛使用的预测模型——AR、LSTM、支持向量机（SVM）、梯度提升和随机森林。此外，我们展示了所提出混合模型的可解释性，这是大多数COVID-19病例黑箱预测模型所不具备的关键特性。我们的研究为构建有效且可解释的数据驱动模型提供了新的且有前景的方向，这将对当前及未来潜在疫情的公共卫生政策制定和防控产生重要影响。